Find tools › Open-source projects › Keep data private

splash

Open-source project · by incoai

Run large AI models locally on your Mac with high speed and low overhead.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Run local language models on Apple Silicon
  • Power local coding agents and chat apps
  • Serve OpenAI-compatible APIs locally

How to start

  1. Install the engine using Homebrew by running brew install incoai/tap/splash in your terminal.

  2. Start the local server with a model using splash serve --model unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M.

  3. Open http://127.0.0.1:8000 in your browser or connect a compatible coding agent.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-17

More detail

A local AI inference engine optimized for Apple Silicon Macs.

Runs large language models locally on macOS with high performance for coding agents and API clients. Reach for this when you want fast local AI inference on Apple hardware.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map